Riz

@Jason Oh snap. Thats smart.

I’ve been saying this for a decade It’s the only solution

Our first dive into Multi-Agent Coordination and Cooperation is here, with Hermes Agent Kanban Orchestrate tasks across multiple agent profiles and dependencies easily and visually. Achieve more. See the docs here: hermes-agent.nousresearch.com/docs/user-guid…

Can I build a cowork | code app where I can switch to different models and be pinned to Claude.

If you work for OpenAI, Anthropic or xAI Please add a 'model'=>'latest' value so I can stop having to change model every 6 months!

@MatthewBerman Had the same feeling yesterday too

reluctantly paid

I’m finding using Opus 4.7 unusable as the default model for everything I do now. I keep hitting rate limits and I’m on the £90 a month Max plan. It just appears to be burning through tokens unnecessarily. Most of my work doesn’t need frontier intelligence, but I’m pretty happy to use a sledgehammer to crack a nut just because I can. I was able to use Opus 4.6 to do everything from creating presentations to generating software. Also it’s just more effort to pick a different model for each task… I’ve now set the default model in Cowork to Opus 4.6 and seems to be effective and not hitting limits - like it was before 4.7 came out. For software tasks in Claude Code I’m using 4.7. These are the frontier tasks I understand the least so want to use the best model. ChatGPT 5.5 and Codex are the default models for my Hermes agents. OpenAI is back, 5.5 is nailing every task in the agent harness. Have very few complaints. And the £20 a month tier is plenty. I use Kimi K2.5 as a back up if I hit any rate limits and it’s also pretty effective. I still can’t stop using Grok on my iPhone. It’s so fast, has a great personality and I love that it scans X for the latest info on whatever casual queries I’m after - usually pancake recipes, finding films to watch and helping me understand the latest updates in AI.

Journalists aren't neutral - they're the cavalry in the culture wars.

I can’t use Opus 4.7. It’s too token intensive and just feels unnecessary. Exclusively back to 4.6 and also very much enjoying 5.5 and codex. OpenAI are certainly back in the game.

@levelsio Fuck this is smart.

P.S. this Mapbox cost is another cost detected by my new Situation Monitor dashboard with AI insights, it scouts all my projects insights on what to improve A few weeks ago it detected the Cloudflare bill was too high and we found they made a mistake which they quickly fixed and refunded Really nice!

@sama So you are using claude for some use cases too?

you know what all of these "which is better" polls are silly use codex or claude code, whatever works best for you i am grateful we live in a time with such amazing tools, and grateful there is a choice

@AzizSunderji Do way more than 2x.

Today's dads do 2x the childcare their fathers did. Where do they find the time? Mainly: they work less. But also: they spend less time relaxing (TV, reading, and other leisure). [1/5]

@Teknium @NousResearch Smart

Introducing Hermes Curator! The new system built in to Hermes Agent now helps you keep your skills that the self improvement loop creates in check, by consolidating and pruning automatically. The curator does multiple things: - keeps track of how often you use each skill, when it was last updated/created, etc - Once a week runs automatically (configurable) - Uses the analytics plus it's own scanning of your skills and consolidates or prunes them if necessary - Skips externally installed skills, built in skills, and skills you "pin" that you dont' want touched. It will only attempt curation over agent created/updated skills or user written skills. - It will then determine whether skills can be consolidated, pruned, or otherwise made more manageable. It will convert some skills that are too specific into references, templates or scripts for larger/broader skills, or integrate them directly into a consolidation of an existing skill. You can also disable it entirely in the config.yaml and/or run it manually with `hermes curator run ` Learn more on the docs here: hermes-agent.nousresearch.com/docs/user-guid…

How do u run codex in cowork?

There is a single thin-film material required by every AI chip on earth. GPUs, TPUs, custom ASICs. All of them. 98% of global supply controlled by one Japanese chemical company. Zero production-ready alternatives. One producer fully booked through 2027. Raising prices. Lead times past 6 months. NVIDIA is so scared they're paying half the capex to expand supplier fabs themselves. The keyword is “umami”. Nobody's talking about this. They will be in about

@sama Yes please keep it

codex with the $20 plan is a really good deal

Happy to announce that Hermes Agent's repo just surpassed Anthropic's Claude Code repo

@Teknium @RoundtableSpace That’s gonna be huge

@RoundtableSpace Agent profile coordinatoon soon 🤗

HERMES AGENT V0.11 JUST DROPPED AND IT LOOKS MORE LIKE A FULL PLATFORM UPDATE THAN A NORMAL RELEASE. New mission control, cleaner terminal UI, unlimited sub agent depth, broader model support, and major upgrades across voice, image, plugins, and the dashboard. x.com/JulianGoldieSE…

Hermes Agent tip of the day: There are 4 ways to deal with the model while its running, - Message it, by default, it will interrupt the agent loop, stopping it and making it respond to your new message - /queue will queue up a message that will fire after the agent loop completes - /bg or /btw will run a parallel prompt that is async And - /steer will inject a guidance message into the next tool calls result sent to the model during an agent loop, to try to guide the rest of its trajectory

Hitting my limit on Opus 4.7 every session on the Max plan. This is quite unacceptable @claudeai ; help me out here?